{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:21:59Z","timestamp":1783045319022,"version":"3.54.6"},"reference-count":168,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQ23F020009"],"award-info":[{"award-number":["LQ23F020009"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62421003"],"award-info":[{"award-number":["62421003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302449"],"award-info":[{"award-number":["62302449"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Virtual Reality & Intelligent Hardware"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.vrih.2026.03.002","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:36:09Z","timestamp":1778762169000},"page":"172-201","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["From architecture to evaluation: A comprehensive review of video generation techniques"],"prefix":"10.1016","volume":"8","author":[{"given":"Rong","family":"ZHANG","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"WANG","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojun","family":"LEI","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"XU","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.vrih.2026.03.002_bib1","series-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib2","series-title":"Scaling laws for autoregressive generative modeling","author":"Henighan","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.002_bib3","series-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"issue":"11","key":"10.1016\/j.vrih.2026.03.002_bib4","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.vrih.2026.03.002_bib5","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3616","article-title":"StyleGAN-V: a continuous video generator with the price, image quality and perks of StyleGAN2","author":"Skorokhodov","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib6","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1526","article-title":"MoCoGAN: decomposing motion and content for video generation","author":"Tulyakov","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.002_bib7","series-title":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV). Snowmass Village","first-page":"1149","article-title":"ImaGINator: conditional spatio-temporal GAN for video generation","author":"Wang","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.002_bib8","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"2849","article-title":"Temporal generative adversarial nets with singular value clipping","author":"Saito","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib9","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"720","article-title":"N\u00fcwa: visual synthesis Pre-training for neural visUal world creAtion","author":"Wu","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib10","series-title":"Computer Vision \u2013 ECCV","first-page":"701","article-title":"Sound2Sight: generating visual dynamics from sound and context","author":"Chatterjee","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.002_bib11","series-title":"Computer Vision \u2013 ECCV","first-page":"204","article-title":"Pose guided human video generation","author":"Yang","year":"2018"},{"issue":"7","key":"10.1016\/j.vrih.2026.03.002_bib12","doi-asserted-by":"crossref","first-page":"12853","DOI":"10.1609\/aaai.v34i07.6982","article-title":"AutoRemover: automatic object removal for autonomous driving videos","volume":"34","author":"Zhang","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.002_bib13","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"1114","article-title":"Coherent online video style transfer","author":"Chen","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib14","series-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","first-page":"1995","article-title":"Conditional GAN with discriminative filter generation for text-to-video synthesis","author":"Balaji","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.002_bib15","series-title":"Proceedings of the 25th ACM International Conference on Multimedia. Mountain View","first-page":"1789","article-title":"To create what you tell: generating videos from captions","author":"Pan","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib16","series-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib17","series-title":"GPT-4 technical report","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib18","series-title":"VideoGPT: video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.002_bib19","series-title":"Latent video transformer","author":"Rakhimov","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.002_bib20","series-title":"KavukcuogluK. Neural discrete representation learning","author":"van den Oord","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.002_bib21","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"15908","article-title":"Text2Video-zero: text-to-image diffusion models are zero-shot video generators","author":"Khachatryan","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib22","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"22690","article-title":"Text2Performer: text-driven human video generation","author":"Jiang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib23","series-title":"Latent-shift: latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib24","series-title":"2022 IEEE International Conference on Image Processing (ICIP)","first-page":"3943","article-title":"HARP: autoregressive latent video prediction with high-fidelity image generator","author":"Seo","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib25","series-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"10.1016\/j.vrih.2026.03.002_bib26","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10674","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"issue":"8","key":"10.1016\/j.vrih.2026.03.002_bib27","doi-asserted-by":"crossref","first-page":"9117","DOI":"10.1609\/aaai.v37i8.26094","article-title":"VIDM: video implicit diffusion models","volume":"37","author":"MeiK","year":"2023","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.002_bib28","series-title":"CogVideo: large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib29","series-title":"Make-a-video: text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib30","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10219","article-title":"MM-diffusion: learning multi-modal diffusion models for joint audio and video generation","author":"Ruan","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib31","series-title":"Free-bloom: zero-shot text-to-video generator with LLM director and LDM animator","author":"Huang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib32","series-title":"VideoComposer: compositional video synthesis with motion controllability","author":"Wang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib33","series-title":"DragNUWA: fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib34","series-title":"Stable video diffusion: scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib35","series-title":"SIGGRAPH Asia 2024 Conference Papers","first-page":"1","article-title":"Lumiere: a space-time diffusion model for video generation","author":"Bar-Tal","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib36","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"22563","article-title":"KreisK. Align your latents: high-resolution video synthesis with latent diffusion models","author":"Blattmann","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib37","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4172","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib38","series-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib39","series-title":"Open-sora: democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib40","series-title":"CogVideoX: text-to-video diffusion models with an expert transformer","author":"Yang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib41","series-title":"HunyuanVideo: a systematic framework for large video generative models","author":"Kong","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib42","series-title":"Wan: open and advanced large-scale video generative models","author":"Wang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib43","series-title":"Generating videos with dynamics-aware implicit generative adversarial networks","author":"Yu","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib44","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"23206","article-title":"Efficient video prediction via sparsely conditioned flow matching","author":"Davtyan","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib45","series-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib46","series-title":"Reuse and diffuse: iterative denoising for text-to-video generation","author":"Gu","year":"2023"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.002_bib47","doi-asserted-by":"crossref","first-page":"3059","DOI":"10.1007\/s11263-024-02295-1","article-title":"LaVie: high-quality video generation with cascaded latent diffusion models","volume":"133","author":"Wang","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.vrih.2026.03.002_bib48","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"205","article-title":"Factorizing text-to-video generation by explicit image conditioning","author":"Girdhar","year":"2024"},{"issue":"7","key":"10.1016\/j.vrih.2026.03.002_bib49","doi-asserted-by":"crossref","first-page":"4177","DOI":"10.1007\/s11263-025-02349-y","article-title":"Swap attention in spatiotemporal diffusions for text-to-video generation","volume":"133","author":"Wang","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.vrih.2026.03.002_bib50","series-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib51","series-title":"LaMD: latent motion diffusion for image-conditional video generation","author":"Hu","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib52","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"7312","article-title":"Structure and content-guided video synthesis with diffusion models","author":"Esser","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib53","series-title":"SEINE: short-to-long video diffusion model for generative transition and prediction","author":"Chen","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib54","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"399","article-title":"DynamiCrafter: animating open-domain images with video diffusion priors","author":"Xing","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib55","series-title":"ConsistI2V: enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib56","series-title":"NWT: Towards natural audio-to-video generation with representation learning","author":"Mama","year":"2021"},{"issue":"7","key":"10.1016\/j.vrih.2026.03.002_bib57","doi-asserted-by":"crossref","first-page":"6639","DOI":"10.1609\/aaai.v38i7.28486","article-title":"Diverse and aligned audio-to-video generation via text-to-video model adaptation","volume":"38","author":"Yariv","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.002_bib58","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"1922","article-title":"DiffTED: one-shot audio-driven TED talk video generation with diffusion-based co-speech gestures","author":"Hogue","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib59","series-title":"MagicAvatar: multimodal avatar generation and animation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib60","series-title":"Ctrl-adapter: an efficient and versatile framework for adapting diverse controls to any diffusion model","author":"Lin","year":"2024"},{"issue":"2","key":"10.1016\/j.vrih.2026.03.002_bib61","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/TVCG.2024.3365804","article-title":"Make-your-video: customized video generation using textual and structural guidance","volume":"31","author":"Xing","year":"2025","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.1016\/j.vrih.2026.03.002_bib62","series-title":"Animate-a-story: storytelling with retrieval-augmented video generation","author":"He","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib63","series-title":"VideoPoet: a large language model for zero-shot video generation","author":"Kondratyuk","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib64","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"22623","article-title":"DreamPose: fashion image-to-video synthesis via stable diffusion","author":"Karras","year":"2023"},{"issue":"5","key":"10.1016\/j.vrih.2026.03.002_bib65","doi-asserted-by":"crossref","first-page":"4117","DOI":"10.1609\/aaai.v38i5.28206","article-title":"Follow your pose: pose-guided text-to-video generation using pose-free videos","volume":"38","author":"Ma","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.002_bib66","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8153","article-title":"Animate anyone: consistent and controllable image-to-video synthesis for character animation","author":"Li","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib67","series-title":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","first-page":"1","article-title":"MotionCtrl: a unified and flexible motion controller for video generation","author":"Wang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib68","series-title":"Motion-conditioned diffusion model for controllable video synthesis","author":"Chen","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib69","series-title":"CameraCtrl: enabling camera control for text-to-video generation","author":"He","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib70","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16773","article-title":"Consistent view synthesis with pose-guided diffusion models","author":"Tseng","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib71","series-title":"Cinematic mindscapes: high-quality video reconstruction from brain activity","author":"Chen","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib72","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18456","article-title":"Video probabilistic diffusion models in projected latent space","author":"Yu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib73","series-title":"Latte: latent diffusion transformer for video generation","author":"Ma","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib74","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10209","article-title":"Notice of removal: VideoFusion: decomposed diffusion models for high-quality video generation","author":"Luo","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib75","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"7255","article-title":"MV-diffusion: motion-aware video diffusion model","author":"Deng","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib76","series-title":"Advances in Neural Information Processing Systems 37","first-page":"84839","article-title":"Visual autoregressive modeling: scalable image generation via next-scale prediction","author":"Jiang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib77","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"393","article-title":"Photorealistic video generation with diffusion models","author":"Gupta","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib78","series-title":"Imagen video: high definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib79","series-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib80","series-title":"MagicVideo: efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib81","series-title":"Any-to-any generation via composable diffusion","author":"Tang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib82","series-title":"VideoGen: a reference-guided latent diffusion approach for high definition text-to-video generation","author":"Li","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib83","series-title":"LAMP: learn a motion pattern for few-shot-based video generation","author":"Wu","year":"2023"},{"issue":"4","key":"10.1016\/j.vrih.2026.03.002_bib84","doi-asserted-by":"crossref","first-page":"1879","DOI":"10.1007\/s11263-024-02271-9","article-title":"Show-1: marrying pixel and latent diffusion models for text-to-video generation","volume":"133","author":"Zhang","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.vrih.2026.03.002_bib85","series-title":"Sora: a review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib86","series-title":"SinFusion: training diffusion models on a single image or video","author":"Nikankin","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib87","series-title":"Advances in Neural Information Processing Systems 35. OrleansNew, Louisiana, USA, Neural Information Processing Systems Foundation","first-page":"23371","article-title":"MCVD - masked conditional video diffusion for prediction, generation, and interpolation","author":"Jolicoeur-Martineau","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib88","series-title":"ControlVideo: training-free controllable text-to-video generation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib89","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18444","article-title":"Conditional image-to-video generation with latent flow diffusion models","author":"Ni","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib90","series-title":"Generative disco: text-to-video generation for music visualization","author":"Liu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib91","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1481","article-title":"MagicAnimate: temporally consistent human image animation using diffusion model","author":"Xu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib92","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6537","article-title":"Dream video: composing your dream videos with customized subject and motion","author":"Wei","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib93","series-title":"Probabilistic adaptation of text-to-video models","author":"Yang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib94","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"27946","article-title":"AnimateAnything: consistent and controllable animation for video generation","author":"Lei","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib95","series-title":"Unsupervised learning for physical interaction through video prediction","author":"Finn","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.002_bib96","series-title":"Advances in Neural Information Processing Systems","first-page":"879","article-title":"PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs","author":"Wang","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib97","series-title":"Generating videos with scene dynamics","author":"Vondrick","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.002_bib98","series-title":"Proceedings of the 25th ACM International Conference on Multimedia. Mountain View","first-page":"1096","article-title":"Sync-DRAW: automatic video generation using deep recurrent attentive architectures","author":"Mittal","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib99","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"1435","article-title":"Attentive semantic video generation using captions","author":"Marwah","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib100","series-title":"Video generation from text","author":"Li","year":"2017"},{"key":"10.1016\/j.vrih.2026.03.002_bib101","series-title":"Proceedings of the 27th ACM International Conference on Multimedia","first-page":"1239","article-title":"Cross-modal dual learning for sentence-to-video generation","author":"Liu","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.002_bib102","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"7589","article-title":"Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation","author":"Wu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib103","series-title":"T2V-turbo-v2: enhancing video generation model post-training through data, reward, and conditional guidance design","author":"Li","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib104","series-title":"Advances in Neural Information Processing Systems 37","first-page":"75692","article-title":"T2V-turbo: breaking the quality bottleneck of video consistency model with mixed reward feedback","author":"Basu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib105","series-title":"Phenaki: variable length video generation from open domain textual description","author":"Villegas","year":"2022"},{"issue":"9","key":"10.1016\/j.vrih.2026.03.002_bib106","doi-asserted-by":"crossref","first-page":"7340","DOI":"10.1109\/TPAMI.2025.3558507","article-title":"MagicTime: time-lapse video generation models as metamorphic simulators","volume":"47","author":"Yuan","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.vrih.2026.03.002_bib107","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10459","article-title":"MAGVIT: masked generative video transformer","author":"Yu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib108","series-title":"MagicVideo-V2: multi-stage high-aesthetic video generation","author":"Wang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib109","series-title":"Diffusion models for video prediction and infilling","author":"H\u00f6ppe","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib110","series-title":"Learning 3D photography videos via self-supervised diffusion on single images","author":"Wang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib111","series-title":"Motion-zero: zero-shot moving object control framework for diffusion-based video generation","author":"Chen","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib112","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA, IEEE","first-page":"12748","article-title":"Learning high fidelity depths of dressed humans by watching social media dance videos","author":"Jafarian","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.002_bib113","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5288","article-title":"MSR-VTT: a large video description dataset for bridging video and language","author":"Xu","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.002_bib114","series-title":"UCF101: a dataset of 101 human actions classes from videos in the wild","author":"SoomroK","year":"2012"},{"key":"10.1016\/j.vrih.2026.03.002_bib115","series-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.002_bib116","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12342","article-title":"Towards automatic learning of procedures from web instructional videos","volume":"32","author":"Zhou","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.vrih.2026.03.002_bib117","series-title":"2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops","first-page":"546","article-title":"Efficient human action recognition by cascaded linear classification","author":"Roth","year":"2009"},{"key":"10.1016\/j.vrih.2026.03.002_bib118","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"510","article-title":"Hollywood in homes: crowdsourcing data collection for activity understanding","author":"Sigurdsson","year":"2016"},{"key":"10.1016\/j.vrih.2026.03.002_bib119","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"706","article-title":"Dense-captioning events in videos","author":"Krishna","year":"2017"},{"issue":"1","key":"10.1016\/j.vrih.2026.03.002_bib120","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1007\/s11263-016-0987-1","article-title":"Movie description","volume":"123","author":"Rohrbach","year":"2017","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.vrih.2026.03.002_bib121","series-title":"How2: a large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.002_bib122","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4991","article-title":"From lifestyle vlogs to everyday interactions","author":"Fouhey","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.002_bib123","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2630","article-title":"HowTo100M: learning a text-video embedding by watching hundred million narrated video clips","author":"Miech","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.002_bib124","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4580","article-title":"VaTeX: a large-scale, high-quality multilingual dataset for video-and-language research","author":"Wang","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.002_bib125","series-title":"Learning video representations from textual web supervision","author":"Stroud","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.002_bib126","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"1708","article-title":"Frozen in time: a joint video and image encoder for end-to-end retrieval","author":"Bain","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib127","series-title":"MERLOT: multimodal neural script knowledge models","author":"Zellers","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.002_bib128","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"407","article-title":"Learning audio-video modalities from image captions","author":"Nagrani","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib129","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5026","article-title":"Advancing high-resolution video-language representation with large-scale video transcriptions","author":"Xue","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib130","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"431","article-title":"MUGEN: a playground for video-audio-text multimodal understanding and GENeration","author":"Hayes","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib131","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14805","article-title":"CelebV-text: a large-scale facial text-video dataset","author":"Yu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib132","series-title":"Youku-mPLUG: a 10 million large-scale Chinese video-language dataset for pre-training and benchmarks","author":"Xu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib133","series-title":"Advances in Neural Information Processing Systems 37. Vancouver, Canada, Neural Information Processing Systems Foundation","first-page":"57240","article-title":"Vript: a video is worth thousands of words","author":"Yang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib134","series-title":"OpenVid-1M: a large-scale high-quality dataset for text-to-video generation","author":"NanK","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib135","series-title":"Advances in Neural Information Processing Systems 37","first-page":"65618","article-title":"VidProM: a million-scale real prompt-gallery dataset for text-to-video diffusion models","author":"Wang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib136","series-title":"InternVid: a large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib137","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8428","article-title":"Koala-36M: a large-scale video dataset improving consistency between fine-grained conditions and video content","author":"Wang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib138","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13320","article-title":"Panda-70M: captioning 70M videos with multiple cross-modality teachers","author":"Chen","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib139","series-title":"Advances in Neural Information Processing Systems 37","first-page":"21236","article-title":"ChronoMagic-bench: a benchmark for metamorphic evaluation of text-to-time-lapse video generation","author":"Cheng","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib140","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7038","article-title":"Snap video: scaled spatiotemporal transformers for text-to-video synthesis","author":"Menapace","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib141","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8850","article-title":"Make pixels dance: high-dynamic video generation","author":"Zeng","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib142","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7310","article-title":"VideoCrafter2: overcoming data limitations for high-quality video diffusion models","author":"Chen","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib143","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"5613","article-title":"T2V2T: text-to-video-to-text fusion for text-to-video retrieval","author":"Kim","year":"2023"},{"issue":"4","key":"10.1016\/j.vrih.2026.03.002_bib144","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.vrih.2026.03.002_bib145","series-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2018"},{"key":"10.1016\/j.vrih.2026.03.002_bib146","series-title":"Improved techniques for training GANs","author":"Salimans","year":"2016"},{"issue":"12","key":"10.1016\/j.vrih.2026.03.002_bib147","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-reference image quality assessment in the spatial domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"10.1016\/j.vrih.2026.03.002_bib148","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a \"completely blind\" image quality analyzer","volume":"20","author":"Mittal","year":"2013","journal-title":"IEEE Signal Processing Letters"},{"key":"10.1016\/j.vrih.2026.03.002_bib149","series-title":"Deep Generative Models for Highly Structured Data Workshop (DGS@ICLR). New Orleans, Louisiana, USA, OpenReview","article-title":"FVD: a new metric for video generation","author":"Unterthiner","year":"2019"},{"key":"10.1016\/j.vrih.2026.03.002_bib150","series-title":"FETV: a benchmark for fine-grained evaluation of open-domain text-to-video generation","author":"Liu","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib151","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"19891","article-title":"Unmasked teacher: towards training-efficient video foundation models","author":"LiK","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib152","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"22139","article-title":"EvalCrafter: benchmarking and evaluating large video generation models","author":"Liu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib153","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"20087","article-title":"Exploring video quality assessment on user generated contents from aesthetic and technical perspectives","author":"Wu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib154","series-title":"CLIPScore: a reference-free evaluation metric for image captioning","author":"Hessel","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.002_bib155","series-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.vrih.2026.03.002_bib156","series-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.vrih.2026.03.002_bib157","series-title":"VAST: a vision-audio-subtitle-text omni-modality foundation model and dataset","author":"Chen","year":"2023"},{"key":"10.1016\/j.vrih.2026.03.002_bib158","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.vrih.2026.03.002_bib159","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4566","article-title":"CIDEr: consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.vrih.2026.03.002_bib160","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"ROUGE: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.vrih.2026.03.002_bib161","series-title":"Proceedings of the Ninth Workshop on Statistical Machine Translation","first-page":"376","article-title":"Meteor universal: language specific translation evaluation for any target language","author":"Denkowski","year":"2014"},{"key":"10.1016\/j.vrih.2026.03.002_bib162","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8406","article-title":"T2V-compbench: a comprehensive benchmark for compositional text-to-video generation","author":"Sun","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib163","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7827","article-title":"SimDA: simple diffusion adapter for efficient video generation","author":"Xing","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib164","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"7589","article-title":"Tune-A-video: one-shot tuning of image diffusion models for text-to-video generation","author":"Wu","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib165","series-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"7561","article-title":"Evaluation agent: efficient and promptable evaluation framework for visual generative models","author":"Zhang","year":"2025"},{"key":"10.1016\/j.vrih.2026.03.002_bib166","series-title":"Evaluation of text-to-video generation models: a dynamics perspective","author":"Liao","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib167","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"21807","article-title":"VBench: comprehensive benchmark suite for video generative models","author":"Huang","year":"2024"},{"key":"10.1016\/j.vrih.2026.03.002_bib168","series-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024"}],"container-title":["Virtual Reality & Intelligent Hardware"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2096579626000173?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2096579626000173?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:05:26Z","timestamp":1783044326000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2096579626000173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":168,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["S2096579626000173"],"URL":"https:\/\/doi.org\/10.1016\/j.vrih.2026.03.002","relation":{},"ISSN":["2096-5796"],"issn-type":[{"value":"2096-5796","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From architecture to evaluation: A comprehensive review of video generation techniques","name":"articletitle","label":"Article Title"},{"value":"Virtual Reality & Intelligent Hardware","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.vrih.2026.03.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"name":"copyright","label":"Copyright"}]}}